© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13847
    Prev
    Next
    INDEX
    Explanations

    specific categories and attributes related to items in biological and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding parentheses

    np_acts-logits-general · gemini-2.0-flash

    lists of items and their descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.54
    VYMaps
    -0.49
     vectorielles
    -0.49
     Numerade
    -0.48
    clusal
    -0.46
    #+#
    -0.43
    strates
    -0.43
    CheckBreak
    -0.41
     themſelves
    -0.41
     AssemblyCulture
    -0.41
    POSITIVE LOGITS
    Clik
    0.42
    뀜
    0.41
    ="@+
    0.40
    Salve
    0.35
    owo
    0.35
    frei
    0.35
     renom
    0.35
     ebenfalls
    0.34
    Share
    0.34
     rene
    0.34
    Activations Density 0.487%

    No Known Activations